{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T17:48:56Z","timestamp":1750441736906,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["951911"],"award-info":[{"award-number":["951911"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592288","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"530-534","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Escaping local minima in deep reinforcement learning for video summarization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0417-9315","authenticated-orcid":false,"given":"Panagiota","family":"Alexoudi","sequence":"first","affiliation":[{"name":"Department of Informatics, Aristotle University of Thessaloniki, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5479-0632","authenticated-orcid":false,"given":"Ioannis","family":"Mademlis","sequence":"additional","affiliation":[{"name":"Department of Informatics, Aristotle University of Thessaloniki, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7555-8641","authenticated-orcid":false,"given":"Ioannis","family":"Pitas","sequence":"additional","affiliation":[{"name":"Department of Informatics, Aristotle University of Thessaloniki, Greece"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037883"},{"volume-title":"International Conference on Multimedia Modeling (MMM). Springer.","author":"Apostolidis E.","key":"e_1_3_2_1_2_1","unstructured":"E. Apostolidis, E. Adamantidou, A.\u00a0I. Metsai, V. Mezaris, and I. Patras. 2020. Unsupervised video summarization via attention-driven adversarial learning. In International Conference on Multimedia Modeling (MMM). Springer."},{"volume-title":"Proceedings of the International Workshop on AI for Smart TV Content Production, Access and Delivery.","author":"Apostolidis E.","key":"e_1_3_2_1_3_1","unstructured":"E. Apostolidis, A.\u00a0I. Metsai, E. Adamantidou, V. Mezaris, and I. Patras. 2019. A stepwise, label-based approach for improving the adversarial training in unsupervised video summarization. In Proceedings of the International Workshop on AI for Smart TV Content Production, Access and Delivery."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the British Machine Vision Conference (BMVC).","author":"Gonuguntla N.","year":"2019","unstructured":"N. Gonuguntla, B. Mandal, and NB Puhan. 2019. Enhanced Deep Video Summarization Network. In Proceedings of the British Machine Vision Conference (BMVC)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NIPS)","author":"Goodfellow I.","year":"2014","unstructured":"I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y.A. Bengio. 2014. Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems (NIPS) (2014)."},{"volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). Springer.","author":"Gygli M.","key":"e_1_3_2_1_6_1","unstructured":"M. Gygli, H. Grabner, H. Riemenschneider, and L. Van\u00a0Gool. 2014. Creating summaries from user videos. In Proceedings of the European Conference on Computer Vision (ECCV). Springer."},{"volume-title":"Proceedings of the International Conference on Machine Learning. PMLR.","author":"Haarnoja T.","key":"e_1_3_2_1_7_1","unstructured":"T. Haarnoja, A. Zhou, P. Abbeel, and S. Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In Proceedings of the International Conference on Machine Learning. PMLR."},{"volume-title":"Proceedings of the ACM International Conference on Multimedia.","author":"He X.","key":"e_1_3_2_1_8_1","unstructured":"X. He, Y. Hua, T. Song, Z. Zhang, Z. Xue, R. Ma, N. Robertson, and H. Guan. 2019. Unsupervised video summarization with attentive conditional Generative Adversarial Networks. In Proceedings of the ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018537"},{"volume-title":"Proceedings of the IEEE International Conference on Image Processing (ICIP).","author":"Kaseris M.","key":"e_1_3_2_1_10_1","unstructured":"M. Kaseris, I. Mademlis, and I. Pitas. 2021. Adversarial unsupervised video summarization augmented with dictionary loss. In Proceedings of the IEEE International Conference on Image Processing (ICIP)."},{"volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).","author":"Kaseris M.","key":"e_1_3_2_1_11_1","unstructured":"M. Kaseris, I. Mademlis, and I. Pitas. 2022. Exploiting Caption Diversity for Unsupervised Video Summarization. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"A. Kulesza and B. Taskar. 2012. Determinantal Point Processes for machine learning. arXiv preprint arXiv:1207.6083 (2012).","DOI":"10.1561\/9781601986290"},{"volume-title":"Proceedings of the IEEE International Workshop on Multimedia Signal Processing (MMSP).","author":"Mademlis I.","key":"e_1_3_2_1_13_1","unstructured":"I. Mademlis, A. Tefas, N. Nikolaidis, and I. Pitas. 2016. Movie shot selection preserving narrative properties. In Proceedings of the IEEE International Workshop on Multimedia Signal Processing (MMSP)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2615289"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Mahasseni B.","key":"e_1_3_2_1_15_1","unstructured":"B. Mahasseni, M. Lam, and S. Todorovic. 2017. Unsupervised video summarization with adversarial lstm networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). Springer.","author":"Potapov D.","key":"e_1_3_2_1_16_1","unstructured":"D. Potapov, M. Douze, Z. Harchaoui, and C. Schmid. 2014. Category-specific video summarization. In Proceedings of the European Conference on Computer Vision (ECCV). Springer."},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Rochan M.","key":"e_1_3_2_1_17_1","unstructured":"M. Rochan and Y. Wang. 2019. Video summarization by learning from unpaired data. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.09.017"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Song Y.","key":"e_1_3_2_1_20_1","unstructured":"Y. Song, J. Vallmitjana, A. Stent, and A. Jaimes. 2015. TVSum: Summarizing web videos using titles. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_21_1","unstructured":"S. Zagoruyko and N. Komodakis. 2017. DiracNets: Training very deep neural networks without skip-connections. arXiv preprint arXiv:1706.00388 (2017)."},{"volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). Springer.","author":"Zhang K.","key":"e_1_3_2_1_22_1","unstructured":"K. Zhang, W.-L. Chao, F. Sha, and K. Grauman. 2016. Video summarization with Long Short-Term Memory. In Proceedings of the European Conference on Computer Vision (ECCV). Springer."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.07.030"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2951680"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"B. Zhao X. Li and X. Lu. 2020. TTH-RNN: Tensor-Train hierarchical recurrent neural network for video summarization. IEEE Transactions on Industrial Electronics (2020).","DOI":"10.1109\/TIE.2020.2979573"},{"volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).","author":"Zhou K.","key":"e_1_3_2_1_26_1","unstructured":"K. Zhou, Y. Qiao, and T. Xiang. 2018. Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)."}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Thessaloniki Greece","acronym":"ICMR '23"},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592288","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:30Z","timestamp":1750178250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":26,"alternative-id":["10.1145\/3591106.3592288","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592288","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}